
import pandas as pd
import numpy as np


# Import graph Libraries
import plotly.express as px
import seaborn as sns
import matplotlib.pyplot as plt
from plotly.subplots import make_subplots
import plotly.graph_objs as go


from plotly.offline import init_notebook_mode
init_notebook_mode(connected=True)


# Text Processing Libraries
import string
import re
import nltk
from wordcloud import WordCloud,STOPWORDS
from sklearn.feature_extraction.text import TfidfVectorizer


#import ML packages
from sklearn.linear_model import LinearRegression
from sklearn.ensemble import RandomForestRegressor,GradientBoostingRegressor
from sklearn.svm import SVR
from xgboost import XGBRegressor
from sklearn.model_selection import cross_val_score
from sklearn.tree import DecisionTreeRegressor
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler


# Loading Data
data = pd.read_csv("AB_US_2020.csv")

C:\Users\soura\anaconda3\lib\site-packages\IPython\core\interactiveshell.py:3165: DtypeWarning:

Columns (4) have mixed types.Specify dtype option on import or set low_memory=False.


data.head()


data.shape

(226030, 17)


data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 226030 entries, 0 to 226029
Data columns (total 17 columns):
 #   Column                          Non-Null Count   Dtype  
---  ------                          --------------   -----  
 0   id                              226030 non-null  int64  
 1   name                            226002 non-null  object 
 2   host_id                         226030 non-null  int64  
 3   host_name                       225997 non-null  object 
 4   neighbourhood_group             110185 non-null  object 
 5   neighbourhood                   226030 non-null  object 
 6   latitude                        226030 non-null  float64
 7   longitude                       226030 non-null  float64
 8   room_type                       226030 non-null  object 
 9   price                           226030 non-null  int64  
 10  minimum_nights                  226030 non-null  int64  
 11  number_of_reviews               226030 non-null  int64  
 12  last_review                     177428 non-null  object 
 13  reviews_per_month               177428 non-null  float64
 14  calculated_host_listings_count  226030 non-null  int64  
 15  availability_365                226030 non-null  int64  
 16  city                            226030 non-null  object 
dtypes: float64(3), int64(7), object(7)
memory usage: 29.3+ MB


data.describe()


# Missing values %
# Count missing values
missing_values = data.isna().sum()
# Get percentage
missing_values= missing_values/data.shape[0] *100
missing_values

id                                 0.000000
name                               0.012388
host_id                            0.000000
host_name                          0.014600
neighbourhood_group               51.252046
neighbourhood                      0.000000
latitude                           0.000000
longitude                          0.000000
room_type                          0.000000
price                              0.000000
minimum_nights                     0.000000
number_of_reviews                  0.000000
last_review                       21.502455
reviews_per_month                 21.502455
calculated_host_listings_count     0.000000
availability_365                   0.000000
city                               0.000000
dtype: float64


# Bar plot for missing values per feature
px.bar(missing_values,title="Missing Percentage",color = missing_values.index)


# Getting features containing numerical features
numrical_df = data.select_dtypes(include=['int64','float64'])


numrical_df.head()


numrical_df.shape

(226030, 10)


# plotting data distributuion of every numerical features
fig = make_subplots(rows=4, cols=2,subplot_titles=numrical_df.columns[2:])

fig.add_trace(
    go.Box(x = numrical_df.latitude,),
    row=1, col=1)
fig.add_trace(
    go.Box(x = numrical_df.longitude,),
    row=1, col=2)
fig.add_trace(
    go.Box(x = numrical_df.price,),
    row=2, col=1)
fig.add_trace(
    go.Box(x = numrical_df.minimum_nights,),
    row=2, col=2)
fig.add_trace(
    go.Box(x = numrical_df.number_of_reviews,),
    row=3, col=1)
fig.add_trace(
    go.Box(x = numrical_df.reviews_per_month,),
    row=3, col=2)
fig.add_trace(
    go.Box(x = numrical_df.calculated_host_listings_count,),
    row=4, col=1)
fig.add_trace(
    go.Box(x = numrical_df.availability_365,),
    row=4, col=2)
fig.show()


# 3D scatter plot between lattitude  longitude and pice to get price clusters
px.scatter_3d(data,x ="latitude",y="longitude",z="price",color= data.room_type)


# How reviews affect duration of stay
px.scatter(x=data.reviews_per_month,y = data.minimum_nights,color=data.room_type)


# Scatter plot between price and minimum nights
px.box(data,x=data.price,color=data.minimum_nights,title = "Price variance With Nights")


# How room type affetcs price
px.box(data,x=data.price,color=data.room_type,title="Price Variance with room_type")


fig = go.Figure()
fig.add_trace(
    go.Scattergeo(lat=data["latitude"],
                  lon=data["longitude"],
                  mode="markers",
                  text=data.price,
                  hoverinfo="text",
                  showlegend=True,
                  name='Price',
                  marker=dict(color="crimson", size=4, opacity=0.8)),
)


fig.update_geos(
    projection_type="orthographic",
    landcolor="green",
    oceancolor="MidnightBlue",
    showocean=True,
    lakecolor="LightBlue",
    projection_rotation_lon=-92,
    projection_rotation_lat=15

)


#Getting features with object type
categorical_df = data.select_dtypes(include=['object'])


categorical_df.head()


# Room type Distribution
px.bar(data.room_type.value_counts(),color=data.room_type.unique(),title="Room_Type")


# Different cities in data
px.bar(data.city.value_counts(),color=data.city.unique(),title="City Counts")


# WordCloud of reviews
text = data.name.dropna()
word_list = " ".join(text.str.lower().values)
plt.figure(figsize=(10,8))
plt.imshow(WordCloud(width=800,height=600,min_font_size=10,stopwords=STOPWORDS).generate(word_list))
plt.title('WordCloud',fontsize=18,fontweight='bold')
plt.axis('off')
plt.show()


# Getting state names from cities
states_dic = {'Asheville':'NC','Austin':'TX','Boston':'MA','Broward County':'FL','Cambridge':'MA','Chicago':'IL','Clark County':'NV','Columbus':'OH','Denver':'CO','Hawaii':'HI','Jersey City':'NJ',
             'Los Angeles':'SC','Nashville':'TN','New Orleans':'MS','New York City':'NY','Oakland':'CA','Pacific Grove':'CA','Portland':'OR','Rhode Island':'RI','Salem':'MA','San Clara Country':'CA',
             'Santa Cruz County':'CA','San Diego':'CA','San Francisco':'CA','San Mateo County':'CA','Seattle':'WA','Twin Cities MSA':'MN','Washington D.C.':'DC'}

categorical_df['state'] = categorical_df['city'].apply(lambda x : states_dic[x])

<ipython-input-28-2df487dc1d9a>:5: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy


# State count in data
px.bar(categorical_df.state.value_counts(),color=categorical_df.state.unique(),title="State Property Counts")


categorical_df["price"] = data.price
# Grouping data with state
state_ = categorical_df.groupby(by='state')
# Get mean price of each state
state_color = state_.price.mean()
px.choropleth(state_color.values,locations=state_color.index,color=state_color.values ,locationmode="USA-states", scope="usa",title='Average Price At Each State', color_continuous_scale=px.colors.diverging.Portland)

<ipython-input-30-5504c8152c8a>:1: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy


# Popularity of a state
categorical_df["number_of_reviews"] = data.number_of_reviews
state_ = categorical_df.groupby(by='state')
# Get mean reviews of each state property
review_color = state_.number_of_reviews.mean()
px.choropleth(review_color.values,locations=review_color.index,color=review_color.values ,locationmode="USA-states", scope="usa",title='Average Reviews At Each State', color_continuous_scale=px.colors.diverging.Portland)

<ipython-input-31-2f4d41f496fe>:1: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy


data = pd.read_csv("AB_US_2020.csv")

C:\Users\soura\anaconda3\lib\site-packages\IPython\core\interactiveshell.py:3165: DtypeWarning:

Columns (4) have mixed types.Specify dtype option on import or set low_memory=False.


# Dropping Null Values
data.drop(["id","host_id","host_name","neighbourhood_group","neighbourhood","last_review"],axis=1,inplace=True)
data.dropna(inplace=True)


numrical_df = data.select_dtypes(include=['int64','float64'])
categorical_df = data.select_dtypes(include=['object'])
numeric_features = numrical_df.columns


# Removing Outliers 10% of lower quartile and 10% from upper data distribution
lower_bound = .10
upper_bound = .90
# Removing Outliers as some property have unexpectedly high/low price
data = data[data['price'].between(data['price'].quantile(lower_bound), data['price'].quantile(upper_bound), inclusive=True)]

data = data[data['minimum_nights'].between(data['minimum_nights'].quantile(lower_bound), data['minimum_nights'].quantile(upper_bound), inclusive=True)]
data = data[data['calculated_host_listings_count'].between(data['calculated_host_listings_count'].quantile(lower_bound), data['calculated_host_listings_count'].quantile(upper_bound), inclusive=True)]
data = data[data['price'].between(data['price'].quantile(lower_bound), data['price'].quantile(upper_bound), inclusive=True)]
data = data[data['price'].between(data['price'].quantile(lower_bound), data['price'].quantile(upper_bound), inclusive=True)]
data = data[data['number_of_reviews'] > 0]


# Features after removing outliers
fig, axes = plt.subplots(nrows=2, ncols=4)
aux = 0
fig.set_figheight(17)
fig.set_figwidth(25)
for row in axes:
    for col in row:
        data[numeric_features[aux]].plot(kind='kde',ax=col)
        col.set_title(numeric_features[aux] +' Distribution',fontsize=16,fontweight='bold')
        aux+=1


# Vectorizing text data
vectorizer = TfidfVectorizer()
name_vector = vectorizer.fit_transform(data.name)


# Getting mean of each value of extracted vector
data.name = np.array(name_vector.mean(axis=1)).ravel()


data.head()


#heat map using Pearson's coefficient
plt.figure(figsize=(16, 6))
sns.heatmap(data.corr(), annot=True)
plt.title('Correlation Heatmap', fontdict={'fontsize':12}, pad=12);


# One hot encoding categorical feature
data_final = pd.get_dummies(data)


# Removing features and target
Y = data_final.price
X = data_final.drop("price",axis=1)


# Splitting data in ration 70:30
X_train,X_test,Y_train,Y_test = train_test_split(X,Y,test_size=0.3)


#numerical pipeline
scaler=StandardScaler()

#apply scaler to numerical data
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)


index = ["LinearRegression","GradientBoostingRegressor","DecisionTreeRegressor","RandomForestRegressor","XGBRegressor"]
results = pd.DataFrame(columns=["MSE","MAE","RMSE"],index=index)


from sklearn.metrics import mean_absolute_error,mean_squared_error
from sklearn.model_selection import GridSearchCV


# Fit Linear Regression
lin_reg = LinearRegression(n_jobs=-1)
lin_reg.fit(X_train,Y_train)

pred_ = lin_reg.predict(X_test)
mae = mean_absolute_error(Y_test,pred_)
mse = mean_squared_error(Y_test,pred_)
rmse = mean_squared_error(Y_test,pred_,squared=False)
# Getting metrics values
print("Mean Squared Error :: ",mse)
print("Mean Absolute Error :: ",mae)
print("Root Mean Squared Error :: ",rmse)

results.loc["LinearRegression"] = [mse,mae,rmse]

Mean Squared Error ::  971.6391289086546
Mean Absolute Error ::  25.86436835895062
Root Mean Squared Error ::  31.171126526140416


# Fit GradientBoostingRegressor and get best parameter 
gbr = GradientBoostingRegressor()
gbr_param_grid = [{"learning_rate":[0.1,0.01,0.001],"n_estimators":[50,100,150]}]
model_gbr = GridSearchCV(gbr,gbr_param_grid,cv=10,scoring="neg_mean_absolute_error")


model_gbr.fit(X_train,Y_train)

GridSearchCV(cv=10, estimator=GradientBoostingRegressor(),
             param_grid=[{'learning_rate': [0.1, 0.01, 0.001],
                          'n_estimators': [50, 100, 150]}],
             scoring='neg_mean_absolute_error')


# Fitting GradientBoostingRegressor with best parameters
gbr_reg = GradientBoostingRegressor(**model_gbr.best_params_)
gbr_reg.fit(X_train,Y_train)

pred_ = gbr_reg.predict(X_test)
# Get Metrics score
mae = mean_absolute_error(Y_test,pred_)
mse = mean_squared_error(Y_test,pred_)
rmse = mean_squared_error(Y_test,pred_,squared=False)

print("Mean Squared Error :: ",mse)
print("Mean Absolute Error :: ",mae)
print("Root Mean Squared Error :: ",rmse)

results.loc["GradientBoostingRegressor"] = [mse,mae,rmse]

Mean Squared Error ::  917.6520978941544
Mean Absolute Error ::  25.089499953326364
Root Mean Squared Error ::  30.292773030776736


# Define DecisionTreeRegressor with parameter grid
tree_reg = DecisionTreeRegressor()
tree_param_grid = [{"max_depth":list(range(1,10)),"max_leaf_nodes":list(range(2,10,2))}]
model_tree = GridSearchCV(tree_reg,tree_param_grid,cv=10,scoring="neg_mean_absolute_error")


model_tree.fit(X_train,Y_train)

GridSearchCV(cv=10, estimator=DecisionTreeRegressor(),
             param_grid=[{'max_depth': [1, 2, 3, 4, 5, 6, 7, 8, 9],
                          'max_leaf_nodes': [2, 4, 6, 8]}],
             scoring='neg_mean_absolute_error')


# Get best parameter and fit model for best metrics
tree_reg = DecisionTreeRegressor(**model_tree.best_params_)
tree_reg.fit(X_train,Y_train)

pred_ = tree_reg.predict(X_test)

mae = mean_absolute_error(Y_test,pred_)
mse = mean_squared_error(Y_test,pred_)
rmse = mean_squared_error(Y_test,pred_,squared=False)

print("Mean Squared Error :: ",mse)
print("Mean Absolute Error :: ",mae)
print("Root Mean Squared Error :: ",rmse)

results.loc["DecisionTreeRegressor"] = [mse,mae,rmse]

Mean Squared Error ::  997.8994684451395
Mean Absolute Error ::  26.295086281579383
Root Mean Squared Error ::  31.589546822408508


forest_reg = RandomForestRegressor(n_jobs=-1)
forest_param_grid = [{"n_estimators":[50,100,200,250],"max_depth":[5,10,25,50],"max_features":[1,2,4,8,10]}]
model_forest = GridSearchCV(forest_reg,forest_param_grid,cv=10,scoring="neg_mean_absolute_error")


model_forest.fit(X_train,Y_train)

GridSearchCV(cv=10, estimator=RandomForestRegressor(n_jobs=-1),
             param_grid=[{'max_depth': [5, 10, 25, 50],
                          'max_features': [1, 2, 4, 8, 10],
                          'n_estimators': [50, 100, 200, 250]}],
             scoring='neg_mean_absolute_error')


forest_reg = RandomForestRegressor(**model_forest.best_params_)
forest_reg.fit(X_train,Y_train)

pred_ = forest_reg.predict(X_test)

mae = mean_absolute_error(Y_test,pred_)
mse = mean_squared_error(Y_test,pred_)
rmse = mean_squared_error(Y_test,pred_,squared=False)

print("Mean Squared Error :: ",mse)
print("Mean Absolute Error :: ",mae)
print("Root Mean Squared Error :: ",rmse)

results.loc["RandomForestRegressor"] = [mse,mae,rmse]

Mean Squared Error ::  863.5057392990154
Mean Absolute Error ::  24.009467182462814
Root Mean Squared Error ::  29.385468165387724


xgb_reg = XGBRegressor(n_jobs=-1)
xgb_param_grid = [{"n_estimators":[10,50,100],"max_depth":[5,10,50],"learning_rate":[0.1,0.01,0.001]}]
model_xgb = GridSearchCV(xgb_reg,xgb_param_grid,cv=10,scoring="neg_mean_absolute_error")


model_xgb.fit(X_train,Y_train)

GridSearchCV(cv=10,
             estimator=XGBRegressor(base_score=None, booster=None,
                                    colsample_bylevel=None,
                                    colsample_bynode=None,
                                    colsample_bytree=None,
                                    enable_categorical=False, gamma=None,
                                    gpu_id=None, importance_type=None,
                                    interaction_constraints=None,
                                    learning_rate=None, max_delta_step=None,
                                    max_depth=None, min_child_weight=None,
                                    missing=nan, monotone_constraints=None,
                                    n_estimators=100, n_jobs=-1,
                                    num_parallel_tree=None, predictor=None,
                                    random_state=None, reg_alpha=None,
                                    reg_lambda=None, scale_pos_weight=None,
                                    subsample=None, tree_method=None,
                                    validate_parameters=None, verbosity=None),
             param_grid=[{'learning_rate': [0.1, 0.01, 0.001],
                          'max_depth': [5, 10, 50],
                          'n_estimators': [10, 50, 100]}],
             scoring='neg_mean_absolute_error')


xgb_reg = XGBRegressor(**model_xgb.best_params_)
xgb_reg.fit(X_train,Y_train)

pred_ = xgb_reg.predict(X_test)

mae = mean_absolute_error(Y_test,pred_)
mse = mean_squared_error(Y_test,pred_)
rmse = mean_squared_error(Y_test,pred_,squared=False)

print("Mean Squared Error :: ",mse)
print("Mean Absolute Error :: ",mae)
print("Root Mean Squared Error :: ",rmse)

results.loc["XGBRegressor"] = [mse,mae,rmse]

Mean Squared Error ::  868.9667286343574
Mean Absolute Error ::  24.038391504117353
Root Mean Squared Error ::  29.478241613677664


results


# Plotting Mean Squared Error for every model
fig = go.Figure()
fig.add_trace(go.Bar(y=results.MSE.values,x =results.MSE.index,marker=dict(color=results.MSE.values) ))
fig.add_trace(go.Line(y = results.MSE.values,x =results.MSE.index))
fig.update_layout(title=go.layout.Title(text="Mean Squared Error",
                                        font=go.layout.title.Font(size=25)))
fig.show()

C:\Users\soura\anaconda3\lib\site-packages\plotly\graph_objs\_deprecations.py:378: DeprecationWarning:

plotly.graph_objs.Line is deprecated.
Please replace it with one of the following more specific types
  - plotly.graph_objs.scatter.Line
  - plotly.graph_objs.layout.shape.Line
  - etc.


# Plotting Mean Absolute Error for every model
fig = go.Figure()
fig.add_trace(go.Bar(y=results.MAE.values,x =results.MAE.index,marker=dict(color=results.MAE.values) ))
fig.add_trace(go.Line(y = results.MAE.values,x =results.MAE.index))
fig.update_layout(title=go.layout.Title(text="Mean Absolute Error",
                                        font=go.layout.title.Font(size=25)))
fig.show()


# Plotting Root Mean Squared Error for every model
fig = go.Figure()
fig.add_trace(go.Bar(y=results.RMSE.values,x =results.RMSE.index,marker=dict(color=results.RMSE.values) ))
fig.add_trace(go.Line(y = results.RMSE.values,x =results.RMSE.index))
fig.update_layout(title=go.layout.Title(text="Root Mean Squared Error",
                                        font=go.layout.title.Font(size=25)))
fig.show()

	id	name	host_id	host_name	neighbourhood_group	neighbourhood	latitude	longitude	room_type	price	minimum_nights	number_of_reviews	last_review	reviews_per_month	calculated_host_listings_count	availability_365	city
0	38585	Charming Victorian home - twin beds + breakfast	165529	Evelyne	NaN	28804	35.65146	-82.62792	Private room	60	1	138	16/02/20	1.14	1	0	Asheville
1	80905	French Chic Loft	427027	Celeste	NaN	28801	35.59779	-82.55540	Entire home/apt	470	1	114	07/09/20	1.03	11	288	Asheville
2	108061	Walk to stores/parks/downtown. Fenced yard/Pet...	320564	Lisa	NaN	28801	35.60670	-82.55563	Entire home/apt	75	30	89	30/11/19	0.81	2	298	Asheville
3	155305	Cottage! BonPaul + Sharky's Hostel	746673	BonPaul	NaN	28806	35.57864	-82.59578	Entire home/apt	90	1	267	22/09/20	2.39	5	0	Asheville
4	160594	Historic Grove Park	769252	Elizabeth	NaN	28801	35.61442	-82.54127	Private room	125	30	58	19/10/15	0.52	1	0	Asheville

	id	host_id	latitude	longitude	price	minimum_nights	number_of_reviews	reviews_per_month	calculated_host_listings_count	availability_365
count	2.260300e+05	2.260300e+05	226030.000000	226030.000000	226030.000000	2.260300e+05	226030.000000	177428.00000	226030.000000	226030.000000
mean	2.547176e+07	9.352385e+07	35.662829	-103.220662	219.716529	4.525490e+02	34.506530	1.43145	16.698562	159.314856
std	1.317814e+07	9.827422e+07	6.849855	26.222091	570.353609	2.103376e+05	63.602914	1.68321	51.068966	140.179628
min	1.090000e+02	2.300000e+01	18.920990	-159.714900	0.000000	1.000000e+00	0.000000	0.01000	1.000000	0.000000
25%	1.515890e+07	1.399275e+07	32.761783	-118.598115	75.000000	1.000000e+00	1.000000	0.23000	1.000000	0.000000
50%	2.590916e+07	5.138266e+07	37.261125	-97.817200	121.000000	2.000000e+00	8.000000	0.81000	2.000000	140.000000
75%	3.772624e+07	1.497179e+08	40.724038	-76.919322	201.000000	7.000000e+00	39.000000	2.06000	6.000000	311.000000
max	4.556085e+07	3.679176e+08	47.734620	-70.995950	24999.000000	1.000000e+08	966.000000	44.06000	593.000000	365.000000

	id	host_id	latitude	longitude	price	minimum_nights	number_of_reviews	reviews_per_month	calculated_host_listings_count	availability_365
0	38585	165529	35.65146	-82.62792	60	1	138	1.14	1	0
1	80905	427027	35.59779	-82.55540	470	1	114	1.03	11	288
2	108061	320564	35.60670	-82.55563	75	30	89	0.81	2	298
3	155305	746673	35.57864	-82.59578	90	1	267	2.39	5	0
4	160594	769252	35.61442	-82.54127	125	30	58	0.52	1	0

	name	host_name	neighbourhood_group	neighbourhood	room_type	last_review	city
0	Charming Victorian home - twin beds + breakfast	Evelyne	NaN	28804	Private room	16/02/20	Asheville
1	French Chic Loft	Celeste	NaN	28801	Entire home/apt	07/09/20	Asheville
2	Walk to stores/parks/downtown. Fenced yard/Pet...	Lisa	NaN	28801	Entire home/apt	30/11/19	Asheville
3	Cottage! BonPaul + Sharky's Hostel	BonPaul	NaN	28806	Entire home/apt	22/09/20	Asheville
4	Historic Grove Park	Elizabeth	NaN	28801	Private room	19/10/15	Asheville

	name	latitude	longitude	room_type	price	minimum_nights	number_of_reviews	reviews_per_month	calculated_host_listings_count	availability_365	city
2	0.000165	35.60670	-82.55563	Entire home/apt	75	30	89	0.81	2	298	Asheville
3	0.000110	35.57864	-82.59578	Entire home/apt	90	1	267	2.39	5	0	Asheville
4	0.000097	35.61442	-82.54127	Private room	125	30	58	0.52	1	0	Asheville
5	0.000080	35.61856	-82.55276	Entire home/apt	134	7	54	0.49	1	294	Asheville
8	0.000127	35.61929	-82.48114	Entire home/apt	71	28	537	5.01	1	207	Asheville

Work Flow :¶

Data Loading and Insights¶

Exploratory Data Analysis¶

Missing values analysis¶

Numeric data analysis¶

Categorical Data Analysis¶

Location Visualisation¶

Data PreProcessing¶

Model Comparison¶

Linear Regression¶

GradientBoostingRegressor¶

Decision Tree Classifier¶

RandomForestRegressor¶

XGBRegressor¶

Model Comparison¶

	MSE	MAE	RMSE
LinearRegression	971.639129	25.864368	31.171127
GradientBoostingRegressor	917.652098	25.0895	30.292773
DecisionTreeRegressor	997.899468	26.295086	31.589547
RandomForestRegressor	863.505739	24.009467	29.385468
XGBRegressor	868.966729	24.038392	29.478242